CN114081625A

CN114081625A - Navigation path planning method, system and readable storage medium

Info

Publication number: CN114081625A
Application number: CN202010760422.4A
Authority: CN
Inventors: 杨君荣; 杨溪; 吕文尔
Original assignee: Shanghai Weiwei Medical Technology Co ltd
Current assignee: Shanghai Weiwei Medical Technology Co ltd
Priority date: 2020-07-31
Filing date: 2020-07-31
Publication date: 2022-02-25
Anticipated expiration: 2040-07-31
Also published as: CN114081625B

Abstract

The invention provides a navigation path planning method, a navigation path planning system and a readable storage medium, wherein the method comprises the following steps: segmenting a natural cavity in the target trachea volume data image to obtain a natural cavity area volume data image; extracting a central line of the natural cavity from a body data image of the natural cavity region to obtain central line body data; acquiring a topological structure of the natural cavity according to the central line body data; and planning a navigation path from the starting point to the target point based on the topological structure. The method obtains the topological structure of the natural cavity based on the naturally determined central line, and plans the navigation path according to the topological structure, so that the optimal navigation path based on the central line of the natural cavity can be obtained, and the accuracy of the navigation path planning of the natural cavity in the target organ is improved.

Description

Navigation path planning method, system and readable storage medium

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a navigation path planning method, a navigation path planning system, and a readable storage medium.

Background

The diagnosis of lung lesions is of increasing importance for the early detection and treatment of lung cancer. The conventional biopsy of lung lesion is to take biopsy sample by inserting a puncture needle directly into the lung by percutaneous puncture, which has the risk of pneumothorax. Studies have shown that pulmonary percutaneous aspiration has a pneumothorax incidence of 20-40%, and pneumothorax is a serious adverse reaction and may be fatal.

A safer mode is that a bronchus endoscope is adopted to carry out biopsy on the lung focus through a natural airway, so that the risk of adverse reaction can be reduced. However, the bronchial tree is complex, needs a doctor with abundant experience to operate, and has strict requirements on the skills of bronchoscope operators. Therefore, the optimal path from the main airway to the target focus is made before the operation, and the guiding of the doctor to operate the endoscope to reach the target focus in the operation has important significance.

Therefore, it is desirable to provide a method for accurately planning the navigation path of the pulmonary bronchoscope, so as to better assist the doctor and improve the diagnosis accuracy.

Disclosure of Invention

The invention aims to provide a navigation path planning method, a navigation path planning system and a readable storage medium, so as to improve the accuracy of navigation path planning of a natural cavity in an organ.

In order to achieve the above object, the present invention provides a navigation path planning method, which includes:

acquiring a target organ volume data image, wherein the target organ is provided with a natural cavity;

segmenting the natural cavity in the target organ volume data image to obtain a natural cavity region volume data image;

extracting a central line of the natural cavity from the body data image of the natural cavity area to obtain central line body data;

acquiring a topological structure of the natural cavity according to the central line body data;

planning a navigation path from a starting point to a target point based on the topological structure;

the starting point is a starting end point in the topological structure, and the target point is a pixel point which is close to a focus position on a central line of the natural cavity.

Optionally, the planning a navigation path from a starting point to a target point based on the topology includes:

based on the topological structure, searching for a plurality of paths from the starting point to the target point through depth-first search;

determining the navigation path from the number of paths.

Optionally, the determining the navigation path from the plurality of paths includes:

providing path information for each path to facilitate a user in selecting a navigation path from the plurality of paths based on the path information.

Optionally, the topological structure includes position coordinates of each end point of the natural orifice and/or a distance between adjacent end points;

the path information of each path comprises the length of each path, wherein the length of each path is calculated according to the position coordinates of each endpoint on each path and/or the distance between adjacent endpoints;

and/or, the topological structure comprises the bending angle of each endpoint in the natural cavity relative to the endpoint of the upper stage;

the path information of each path comprises the maximum bending angle on each path, wherein the maximum bending angle on each path is determined according to the maximum value of the bending angle of each end point on each path relative to the end point at the previous stage.

Optionally, the obtaining the topological structure of the natural orifice according to the central line body data includes:

step A1, regarding the central line body data, taking an end point of an initial position of the natural orifice as the initial end point of the topological structure, and taking the initial end point as a current point;

b1, performing neighborhood traversal on the current point, if only one valid point exists in the neighborhood, executing step C1, and if a plurality of valid points exist in the neighborhood, executing step D1;

step C1, using the effective point as the current point, and returning to execute step B1;

step D1, marking the current point as an end point of the turnout junction, sequentially taking each effective point in the neighborhood of the current point as the current point, and returning to execute the step B1;

and E1, judging whether the effective points of the central line body data are traversed completely, if not, returning to execute the step B1, and if so, exiting the cycle and combining all the end points to obtain the topological structure of the natural orifice.

Optionally, the method further includes:

in the process of loop iteration to obtain the topological structure of the natural cavity, the distance between each end point is obtained, and the bending angle of each end point relative to the upper-stage end point is calculated.

Optionally, the extracting a centerline of the natural orifice from the volume data image of the natural orifice region to obtain centerline body data includes:

performing 3D distance transformation on each natural cavity region pixel point in the natural cavity region volume data image to obtain natural cavity distance transformation volume data;

and carrying out three-dimensional refining operation on the natural cavity distance transformation volume data to obtain centerline body data.

Optionally, the performing 3D distance transformation on each natural orifice region volume pixel point in the natural orifice region volume data image includes:

and traversing the peripheral neighborhood from near to far by taking the natural cavity region volume pixel point as a reference point to find the nearest unnatural cavity region volume pixel point aiming at each natural cavity region volume pixel point in the natural cavity region volume data image, and calculating the linear distance between the natural cavity region volume pixel point and the unnatural cavity region volume pixel point as the pixel value corresponding to the natural cavity region volume pixel point.

Optionally, the three-dimensional refining operation is performed on the natural orifice distance transformation volume data to obtain centerline body data, including:

traversing each voxel point V in the natural orifice distance transformation volume data, and if a first preset condition is met, determining the voxel point V as a central line body pixel point;

the first preset condition is as follows: d_v>d_viAnd d is_v>d_vjAnd | d_vi-d_vj|<Epsilon, i belongs to Zf, j belongs to Zs; where ε is a first threshold value, d_vTransforming the data value, d, in the volume data for the volume pixel point V at the natural lumen distance_viThe data value d of the ith individual pixel point in the set Zf in the natural cavity distance transformation volume data_vjAnd forming a symmetrical voxel point pair in the neighborhood of the voxel point V by the ith individual pixel point in the set Zf and the jth individual pixel point in the set Zs for the data value of the jth individual pixel point in the set Zs in the natural cavity distance transformation volume data.

Optionally, the segmenting the natural cavity in the target organ volume data image to obtain the natural cavity region volume data image includes:

detecting the initial position of the natural cavity in the target organ volume data image, and determining a region growing seed point;

and segmenting the natural cavity by region growing to obtain a data image of the region body of the natural cavity.

Optionally, the detecting a starting position of the natural cavity in the target organ volume data image and determining a region growing seed point include:

step A2, taking a layer of two-dimensional image at the upper end in the target organ volume data image as an initial image;

step B2, binarizing the initial image, calculating the areas and ellipticities of different connected domains in the initial image, and taking the connected domains of which the areas and ellipticities meet second preset conditions as potential cavity areas;

step C2, respectively calculating N layers of two-dimensional images adjacent to the initial image to obtain N potential cavity areas, wherein N is more than or equal to 3;

and D2, respectively calculating the centroid coordinates of the N +1 potential cavity regions, if the deviation between two adjacent centroid coordinates is smaller than a second threshold value, determining the centroid of the initial image as a region growing seed point, otherwise, taking the next two-dimensional image of the initial image as the initial image and returning to execute the step B2.

Optionally, before extracting the centerline of the natural orifice from the volume data image of the natural orifice region, the method further includes:

and filling holes inside the natural cavity in the data image of the natural cavity region by using morphological operation.

Optionally, before segmenting the natural cavity in the target organ volume data image, the method further includes:

and performing edge enhancement processing on the target organ volume data image.

Optionally, the target organ is a lung.

In order to achieve the above object, the present invention further provides a navigation path planning system, which includes a processor and a memory, where the memory stores instructions, and when the instructions are executed by the processor, the navigation path planning method described above is implemented.

In order to achieve the above object, the present invention further provides a readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method for planning a navigation path as described above is implemented.

Compared with the prior art, the navigation path planning method, the navigation path planning system and the storage medium have the following advantages: after a target organ volume data image is obtained, firstly, the natural orifice in the target organ volume data image is segmented to obtain a natural orifice region volume data image, then, a center line of the natural orifice is extracted from the natural orifice region volume data image to obtain centerline body data, then, a topological structure of the natural orifice is obtained according to the centerline body data, and finally, a navigation path from a starting point to a target point is planned based on the topological structure. The method obtains the topological structure of the natural cavity based on the center line of the natural cavity, plans the navigation path according to the topological structure, obtains the optimal navigation path based on the center line of the natural cavity, improves the accuracy of the planning of the natural cavity navigation path in the target organ, further can provide angle information passing through each crossing on the navigation path, provides more comprehensive path planning information, and can better assist doctors to improve the diagnosis accuracy. In addition, the invention can automatically plan the navigation path, reduces the complicated operation of man-machine interaction and improves the diagnosis efficiency. In addition, the navigation path planning algorithm of the invention has strong universality, realizes the end-to-end algorithm flow and further improves the diagnosis efficiency and accuracy.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flow chart of a navigation path planning method according to an embodiment of the present invention;

FIG. 2a is a slice image of the main airway region of the lungs;

fig. 2b is an exemplary view of a segmented three-dimensional bronchial tree;

fig. 2c is a schematic view of a bronchial tree centerline extracted from the bronchial tree shown in fig. 2 b;

fig. 3a is a schematic view of the topology of the bronchial tree acquired from the centerline of the bronchial tree shown in fig. 2 c;

fig. 3b is a schematic view of a navigation path planning according to the bronchial tree topology shown in fig. 3 a;

fig. 4 is a schematic structural diagram of a navigation path planning system according to an embodiment of the present invention.

Detailed Description

The navigation path planning method, system and storage medium according to the present invention will be described in further detail with reference to the accompanying drawings and embodiments. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are all used in a non-precise scale for the purpose of facilitating and distinctly aiding in the description of the embodiments of the present invention. To make the objects, features and advantages of the present invention comprehensible, reference is made to the accompanying drawings. It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the implementation conditions of the present invention, so that the present invention has no technical significance, and any structural modification, ratio relationship change or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The invention provides a navigation path planning method, a system and a storage medium, which are used for improving the accuracy of the navigation path planning of the natural orifice of an organ.

It should be noted that the navigation path planning method according to the embodiment of the present invention may be applied to a navigation path planning system according to the embodiment of the present invention, where the navigation path planning system may be a personal computer, a mobile terminal, and the mobile terminal may be a hardware device with various operating systems, such as a mobile phone and a tablet computer.

The navigation path planning method provided by the invention is described in detail below by taking a target organ as a lung organ as an example, and a lung bronchial tree is a natural lumen in the lung organ. It will be appreciated by those skilled in the art that the present invention may be used for navigation path planning of natural lumens in other organs, such as the intestinal tract, in addition to the navigation path planning of the pulmonary bronchial tree.

Referring to fig. 1, when the present invention is applied to navigation path planning of a pulmonary bronchial tree, the method specifically includes the following steps:

step S100: a lung volume data image is acquired.

In this implementation, the lung volume data image may be a Computed Tomography (CT) volume data image of a patient, but may also be other types of medical images. It should be noted that the size of the lung volume data image may be set according to specific situations, and the invention is not limited to this, for example, the three-dimensional data size of the lung volume data image may be 512 × 512 × 327.

Step S200: and segmenting the bronchial tree from the lung volume data image to obtain a bronchial region volume data image.

The bronchus region volume data image is the natural cavity region volume data image of the lung. In this embodiment, a region growing method may be used to segment the three-dimensional bronchial tree, where pixels with similar properties in the image are combined to form a region. Specifically, a seed pixel is found in a region to be segmented as a starting point for growth, and then pixels (the same or similar properties can be determined according to a predetermined growth or similar criterion) in the neighborhood around the seed pixel, which have the same or similar properties as the seed pixel, are merged into the region where the seed pixel is located. The above process continues with these new pixels as new seed pixels until no more pixels that satisfy the condition can be included, and a region grows.

Preferably, before performing step S200, the method further includes: and performing edge enhancement processing on the lung volume data image to enhance the bronchial wall and improve the image quality of the organ image of the lung volume data image. Specifically, the image edge enhancement can be performed by using laplacian sharpening, and the basic idea of laplacian sharpening is as follows: when the central pixel gray level of a neighborhood is lower than the average gray levels of other pixels in the neighborhood where the central pixel is located, the central pixel should be further reduced; this central pixel should be further enhanced when the gray level of the central pixel in the neighborhood is higher than the average gray level of the other pixels in the neighborhood where it is located. The lung volume data image is convolved by adopting a Laplace second-order template operator, so that the image enhancement is realized, and the edge and the detail of the image are improved. In other embodiments, other image enhancement methods may be employed.

Preferably, the main airway (i.e. the initial part of the natural orifice of the lung) may be detected in the lung volume data image, the region growing seed point may be determined, and then the bronchial tree may be segmented by region growing to obtain the bronchial region volume data image.

Specifically, the main airway can be detected in the lung volume data image in a cyclic iterative manner, and the region growing seed point can be determined:

step A2, taking a layer of two-dimensional image at the upper end in the lung volume data image as an initial image;

step B2, binarizing the initial image, calculating the areas and ellipticities of different connected domains in the initial image, and taking the connected domains of which the areas and ellipticities meet second preset conditions as potential main airway areas;

step C2, respectively calculating N layers of two-dimensional images adjacent to the initial image to obtain N potential main air channel areas, wherein N is more than or equal to 3;

and D2, respectively calculating the centroid coordinates of the N +1 potential main airway regions, if the deviation between two adjacent centroid coordinates is smaller than a second threshold value, determining the centroid of the initial image as a region growing seed point, and otherwise, taking the next two-dimensional image of the initial image as the initial image and returning to execute the step B2.

Fig. 2a shows a slice image of the main airway region of the lungs, with the small black circular region in the middle of fig. 2a being the main airway cross-section and the larger black regions on both sides being the lung region cross-section. Specifically, since the main airway is usually located at the upper end of the lung volume data image, the main airway can be detected from an axial slice image located at the upper end in the lung volume data image, for example, from the 10 th axial slice image, which is taken as the initial image. Preferably, in the lung volume data image, the main airway is usually located in the middle region of the slice image, so a fixed search region can be defined in the initial image, for example, the fixed search region is translated upwards from the center of the initial image by a certain distance (for example, 50 pixels) to serve as the center of the search region, the length and width of the search region can be set to be 50 pixels, and the search region is binarized by using a certain threshold value (for example, -800 HU). Calculating the area and the ellipticity of different connected domains in the search area respectively (for a binary image, the area is the number of pixels in the connected domains, and the ellipticity is the aspect ratio of the minimum circumscribed rectangle), when the area and the ellipticity of a certain connected domain satisfy a second preset condition, for example, the second preset condition may be: an area in the range of [150,450] and an ellipticity greater than 0.8, the connected component is considered to be a potential primary airway region. Then, respectively calculating 3 layers of slice images adjacent to the initial image to obtain 4 potential areas, respectively calculating the centroid coordinates of each potential area, and when the deviation between the centroid coordinates of the potential areas in two adjacent slice images is smaller than a second threshold (for example, 3 pixels), indicating that the centroid in the initial image is the trachea interface center and can be used as a seed point for area growth; otherwise, the potential region is emptied, the next slice image of the current initial image is used as the initial image, and iteration is performed again until the region growing seed point is found.

When the region growing is performed to obtain the three-dimensional bronchial tree, an initial threshold T1 may be set (T1 may be from-830 to-930 HU, for example, -915HU), and the 3-dimensional 26 neighborhood is used to determine the neighboring pixels around the region growing seed point: if the pixel value T of the adjacent pixel is less than T1, the adjacent pixel is considered to be located in the bronchus region, and the pixel value of the pixel is set to be 1; if the pixel value T > T1 of the adjacent pixel, the adjacent pixel is considered to be located in the non-bronchial region, and the pixel value of the adjacent pixel is set to 0. By performing loop iteration in the lung volume data image in this way, a bronchial region can be extracted from the lung volume data image, and finally a bronchial region volume data image is obtained, i.e. the three-dimensional bronchial tree shown in fig. 2b is obtained.

Preferably, before performing step S300, the method may further include: and filling holes inside the bronchial tree in the bronchial region volume data image by using morphological operation. Since there may be a hole inside the segmented bronchial tree, that is, there is a pixel with a pixel value of 0 inside the bronchial tree, it needs to be filled, specifically, the pixel value of the pixel is changed from 0 to 1 by using a hole filling operation in the morphological operation.

Step S300: and extracting the central line of the bronchial tree from the bronchial region volume data image to obtain central line body data.

Specifically, 3D distance conversion may be performed on each bronchial region volume pixel point in the bronchial region volume data image to obtain bronchial distance conversion volume data, and then three-dimensional refinement operation may be performed on the bronchial distance conversion volume data to obtain centerline body data.

The 3D distance transformation process specifically includes: and aiming at each bronchial region body pixel point in the bronchial region body data image, traversing the peripheral neighborhood from near to far by taking the bronchial region body pixel point as a reference point to find the nearest non-bronchial region body pixel point, and calculating the linear distance between the bronchial region body pixel point and the non-bronchial region body pixel point as a pixel value corresponding to the bronchial region body pixel point.

As described above, in the bronchial region volume data image obtained in step S200, the bronchial region volume pixel values are all 1, and the non-bronchial region volume pixel values are 0, so that for all volume pixel points in the bronchial region, the volume pixel points in the peripheral neighborhood of each volume pixel point are traversed from near to far, the closest volume pixel point having a volume pixel value of 0 is found, and the straight-line distance between the two is calculated as the pixel value corresponding to the bronchial region volume pixel point. And circularly traversing all the Volume pixel points in the bronchial region according to the above mode, and finally obtaining pixel values corresponding to all the Volume pixel points in the bronchial region, namely the bronchial distance transformation Volume data Volume _ Dist. In the bronchial distance transformation Volume data Volume _ Dist, the closer the Volume pixel point to the boundary of the bronchial region, the smaller the pixel value, the closer the Volume pixel point inside the bronchial lumen, the larger the pixel value, and the pixel values of the Volume pixel points on both sides of the Volume pixel point on the centerline of the bronchial tree (also referred to as the bronchial tree skeleton) are approximately symmetrical with respect to the skeleton.

Then, performing three-dimensional thinning operation on the bronchial distance transformation volume data, specifically: traversing each voxel point V in the bronchus distance transformation volume data, and if a first preset condition is met, determining the voxel point V as a central line body pixel point;

the first preset condition is as follows: d_v>d_viAnd d is_v>d_vjAnd | d_vi-d_vj|<Epsilon, i belongs to Zf, j belongs to Zs; where ε is a first threshold value, d_vTransforming the data value in the volume data for the volume pixel point V in the bronchial distance, d_viThe data value of the ith individual pixel point in the set Zf in the bronchial distance transformation volume data, d_vjAnd for the data value of the jth individual pixel point in the set Zs in the bronchus distance transformation volume data, the ith individual pixel point in the set Zf and the jth individual pixel point in the set Zs form a symmetrical volume pixel point pair in the neighborhood of the volume pixel point V.

The image thinning is a process of shrinking the binary image, the binary image is reduced in equal proportion according to the original shape, and the original shape is still kept even if the binary image is shrunk to a small degree on a skeleton connecting line domain.

For example, in the bronchus distance transformation Volume data Volume _ Dist, a certain point is selected as a current Volume pixel point V, pixel points in 26 neighborhoods of the current Volume pixel point V can form 13 groups of symmetrical pixel point pairs based on the Volume pixel point V, one pixel point in each group of symmetrical pixel point pairs is put into a set Zf, the other pixel point is put into a set Zs, and the data value of the ith pixel point in the set Zf is d_vi(the data value is the distance value calculated in the 3D distance transformation), the data value of the jth pixel point in the set Zs is D_vj. When the above preset condition is satisfied, which means that when the precursor pixel V is a central line pixel (also called a skeleton pixel), the first threshold may be set according to practical situations, for example, set to 2.

And circularly traversing all the voxel pixels on the bronchus distance transformation voxel data Volume _ Dist according to the above mode, wherein the obtained each centerline voxel pixel forms a skeleton, namely the centerline voxel data Volume _ points, as shown in fig. 2 c.

Step S400: and acquiring the topological structure of the bronchial tree according to the central line body data.

As can be seen from the foregoing description, the centerline of the bronchial tree extracted in step S300 has only a single-pixel width, so that a loop iteration can be performed on the basis of the centerline body data to obtain the topology of the bronchial tree. The method comprises the following specific steps:

step A1, regarding the central line body data, taking a top point on a main airway as the starting end point of the topological structure, and taking the starting end point as a current point;

and E1, judging whether the effective points of the central line body data are completely traversed, if not, returning to execute the step B1, if so, exiting from the circulation, and combining all the end points to obtain the topological structure of the bronchial tree.

It should be noted that the valid point refers to a new point that is not traversed in the neighborhood of the current point. In this embodiment, in the process of traversing from top to bottom in the central line body data, when the current point is not bifurcated, the valid point is directly below the current point, and when the current point is bifurcated, the valid point is below left and below right of the current point.

According to the above iterative loop process, the crossings of the bronchial tree can be found, which also correspond to the endpoints in the topology. Finding each bifurcation can then obtain the topology of the bronchial tree. Fig. 3a schematically shows the topology obtained from the bronchial tree shown in fig. 2c over a loop iteration. Meanwhile, in the above loop iteration process, the distance between the endpoints can be obtained, and the bending angle of each endpoint relative to the endpoint of the previous stage can be calculated.

It can be understood that, for the central line body data Volume _ points, there is a feature that the pixel value of the pixel point on the central line is 1, and the pixel value of the pixel point on the non-central line is 0. In the loop iteration, the upper vertex p1 of the main airway in the center line (i.e. the starting endpoint in the topology) is selected as the current point Pcur, and the initial step w is set_1-21, 0 is the initial angle;

performing 26 neighborhood traversal on the current point Pcur, and indicating that the current point is in a single channel when only one effective point with the pixel value of 1 exists in the neighborhood, and setting the step length w_1-2Increasing 1, setting the pixel value of the point Psource to be-1, taking the next point Pnext found as the current point Psource, and changing the current point into Ppprev;

if a plurality of valid points with the pixel value of 1 appear in the current point Pcur neighborhood, the valid points indicateWhen the current point Pcur reaches the bifurcation of the bronchial tree, the current point Pcur is taken as an end point p2 to be recorded, and the w at the moment is recorded_1-2Value (w at this time)_1-2The value is the distance between the endpoints p2 and p 1). For each effective point in the neighborhood, respectively calculating and recording a cosine angle (the cosine angle is a bending angle representing the next-stage endpoint relative to the current endpoint) between the effective point and the Pprev point, and sequentially taking each Pnext point in the neighborhood as the current point to perform the traversal iteration as described above;

and (3) circularly traversing, and exiting the loop when the valid points in the central line Volume data Volume _ points are all-1 to obtain a topological structure, wherein coordinates of end points of each turnout of the bronchial tree, distances between the end points and a bending angle of each end point relative to an upper-level end point can also be recorded in the topological structure, as shown in fig. 3 a. It should be noted that the cosine angle is used to describe the turning angle of the trachea at the bifurcation point of the bronchial tree in the three-dimensional space, as can be seen from fig. 2b, when the main airway enters the right bronchus, the turning angle needs to be turned to the right side, and the cosine angle can quantitatively describe the turning degree at this point.

Step S500: and planning a navigation path from the starting point to the target point based on the topological structure.

The starting point is a starting end point in the topological structure, and the target point is a pixel point which is on the central line of the bronchial tree and is adjacent to the focus position.

In this embodiment, the coordinates [ x, y, z ] of the location of the lesion outside the bronchus may be manually entered by the physician, where z is the number of slice layers in the lung volume data image. And determining a pixel point adjacent to the focus position on the central line of the bronchial tree according to the coordinates of the focus position, wherein the pixel point is the target point. For example, the pixel point may be a pixel point on the central line of the bronchial tree closest to the lesion position, and the specific determination method is as follows: traversing all effective pixel points (the effective pixel points are pixel points on the central line of the bronchial tree) in the central line body data Volume _ points, calculating the Euclidean distance from the position coordinates of the focus, and obtaining the pixel point corresponding to the minimum distance as the target point and also as a potential point for puncture in the operation.

Based on the topology of the bronchial tree, several paths from the starting point to the target point may be found by a depth-first search, and the navigation path is then determined from the several paths. Specifically, the system may recommend a route to the user as the navigation route, and may also provide route information for each route, so that the user can select a navigation route from the plurality of routes according to the route information.

In this embodiment, the navigation path may be determined based on the path with the least distance and the path with the least turns. In an implementation manner, as described above, the topological structure includes position coordinates of each endpoint of the bronchial tree and/or a distance between adjacent endpoints, so that after a plurality of paths are obtained through searching, the length of each path may be calculated according to coordinates of each endpoint included in each path, or the length of each path may be calculated according to the distance between adjacent endpoints included in each path, and then the system may recommend a path with the shortest length to the user as the navigation path, or provide the length of each path, so that the user selects the path with the shortest length as the navigation path based on the principle of shortest path.

In another implementation, the topology further includes a bending angle of each end point in the bronchial tree relative to the end point at the previous level, so that after several paths are searched, the maximum bending angle in each path can be determined, and the maximum bending angle on each path can be provided. It will be appreciated that if the curve angle at the bifurcation is too large, the bronchoscope may not be able to reach, and therefore the system may recommend the path with the smallest maximum curve angle as the navigation path to the user, or provide the largest curve angle on each path for the user to select the path with the smallest maximum curve angle as the navigation path based on the principle of least curve.

Preferably, the system may recommend an appropriate path to the user as the navigation path in combination with the shortest path rule and the minimum turning rule, or simultaneously provide the length information of each path and the maximum bending angle information on each path, so that the user can select an appropriate navigation path in combination with the two information.

Taking the topology shown in fig. 3a and 3b as an example, the method for depth-first path search is described below, where a root node of the bronchial tree is p1, and the search is performed through the following loop iteration:

step a, firstly taking p1 as a current node, wherein the node p1 has an adjacent node p2, and the distance between the nodes p1 and p2 is recorded as w_1-2；

B, enabling adjacent nodes of the node p2 to be p3 and p4, respectively traversing all adjacent nodes of p2 in the step a, and recording the distance between corresponding nodes;

and c, exiting the loop after all the nodes are traversed, and obtaining paths from the node p1 to all the nodes at the moment.

In fig. 3a and 3b, the large circle point represents the position of the target point, and according to the position of the target point, several paths from the starting point p1 to the target point can be obtained, from which the path with the smallest path length is selected as the navigation path. The most curved angle in the path can also be selected because a portion of the bifurcation is more curved and the bronchoscope cannot reach it. Fig. 3b schematically shows a navigation path drawn by the above method, which navigation path is shown bold in the topology.

In summary, according to the navigation path planning method provided in this embodiment, after obtaining the lung volume data image, the bronchial tree is first segmented from the lung volume data image to obtain a bronchial region volume data image, then the centerline of the bronchial tree is extracted from the bronchial region volume data image to obtain centerline data, then the topology structure of the bronchial tree is obtained according to the centerline data, and finally a navigation path from a starting point to a target point is planned based on the topology structure. According to the method and the device, the topological structure of the bronchial tree is obtained based on the central line of the bronchial tree, the navigation path is planned according to the topological structure, the optimal navigation path based on the lumen central line of the lung trachea is obtained, the accuracy of the lung trachea navigation path planning is improved, further, angle information passing through each bifurcation on the navigation path can be provided, more comprehensive path planning information is provided, and a doctor can be better assisted to improve the diagnosis accuracy. In addition, the navigation path planning can be automatically carried out, the complex operation of man-machine interaction is reduced, and the diagnosis efficiency is improved. In addition, the navigation path planning algorithm of the embodiment has strong universality, realizes an end-to-end algorithm process, and further improves the diagnosis efficiency and accuracy.

Based on the above inventive concept, the present invention also provides a navigation path planning system, as shown in fig. 4, the navigation path planning system 200 may include a processor 210 and a memory 220, where the memory 220 stores instructions, and when the instructions are executed by the processor 210, the steps in the navigation path planning method as described above may be implemented.

Among other things, processor 210 may perform various actions and processes in accordance with instructions stored in memory 220. In particular, the processor 210 may be an integrated circuit chip having signal processing capabilities. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. Various methods, steps and logic blocks disclosed in embodiments of the invention may be implemented or performed. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which may be the X86 architecture or the ARM architecture or the like.

The memory 220 stores executable instructions that, when executed by the processor 210, perform the navigation path planning method described above. The memory 220 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchronous Link Dynamic Random Access Memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memories of the methods described herein are intended to comprise, without being limited to, these and any other suitable types of memory.

Based on the same inventive concept, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the navigation path planning method described above can be implemented.

Similarly, computer-readable storage media in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. It should be noted that the computer-readable storage media described herein are intended to comprise, without being limited to, these and any other suitable types of memory.

It is to be noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In general, the various exemplary embodiments of this invention may be implemented in hardware or special purpose circuits, software, firmware, logic or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of the embodiments of the invention may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

It should be noted that, in the present specification, all the embodiments are described in a related manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the system and the computer-readable storage medium, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.

The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.

Claims

1. A navigation path planning method is characterized by comprising the following steps:

2. The navigation path planning method according to claim 1, wherein planning the navigation path from the start point to the target point based on the topology includes:

determining the navigation path from the number of paths.

3. The method of claim 2, wherein determining the navigation path from the plurality of paths comprises:

4. The navigation path planning method according to claim 3, wherein the topological structure comprises position coordinates of respective end points of the natural orifice and/or a distance between adjacent end points;

5. The navigation path planning method according to claim 1, wherein the obtaining the topology of the natural orifice from the central line body data includes:

6. The navigation path planning method of claim 5, further comprising:

7. The navigation path planning method according to claim 1, wherein the extracting a centerline of the natural orifice from the image of the volume data of the natural orifice region to obtain centerline body data includes:

8. The method for planning a navigation path according to claim 7, wherein the performing 3D distance transformation on each natural lumen region volume pixel point in the natural lumen region volume data image comprises:

9. The navigation path planning method according to claim 7, wherein the performing three-dimensional refinement operation on the natural orifice distance transform volume data to obtain centerline body data comprises:

10. The method for planning a navigation path according to claim 1, wherein the segmenting the natural cavity in the target organ volume data image to obtain the natural cavity region volume data image comprises:

11. The method for planning a navigation path according to claim 10, wherein the detecting a starting point of the natural cavity in the target organ volume data image and determining a region growing seed point comprises:

12. The navigation path planning method according to claim 1, further comprising, before extracting the center line of the natural orifice from the natural orifice region volume data image:

13. The navigation path planning method according to claim 1, further comprising, before segmenting the natural lumen in the target organ volume data image:

14. The navigational path planning method of any of claims 1 to 13, wherein the target organ is a lung.

15. A navigation path planning system comprising a processor and a memory, the memory having stored thereon instructions that, when executed by the processor, carry out the method of any of claims 1 to 14.

16. A readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 14.